Skip to content

update faq#8128

Merged
slin000111 merged 27 commits intomodelscope:mainfrom
slin000111:main
Mar 1, 2026
Merged

update faq#8128
slin000111 merged 27 commits intomodelscope:mainfrom
slin000111:main

Conversation

@slin000111
Copy link
Collaborator

PR type

  • Bug Fix
  • New Feature
  • Document Updates
  • More Models or Datasets Support

PR information

Write the detail information belongs to this PR.

Experiment results

Paste your experiment result here(if needed).

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request focuses on enhancing the clarity and accuracy of the project's Frequently Asked Questions documentation. By updating existing entries, removing outdated information, and providing more direct references to examples, the changes aim to improve the user experience and reduce potential confusion for users interacting with Swift 3.0+ features, particularly regarding parameter usage, model fine-tuning, and deployment configurations.

Highlights

  • FAQ Updates for Swift 3.0+: Clarified the usage of the check_dataset_strategy parameter and get_default_template_type in Swift 3.0 and later versions.
  • Deepseek R1 671B Fine-tuning Example: Replaced a complex explanation for fine-tuning deepseek R1 671B with a direct reference to a relevant example.
  • Removed Outdated FAQ Entry: Deleted an FAQ entry (Q83) concerning LoRA-trained reward models, as it is no longer relevant.
  • Megatron-Swift Checkpoint Saving: Updated the answer for saving checkpoints per epoch in Megatron-Swift, directing users to the save_strategy command-line parameter.
  • Deployment Inference Timeout: Provided updated guidance on setting request timeouts for Swift 3.0+ deployment inference using the SWIFT_TIMEOUT environment variable or InferClient parameters.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog
  • docs/source/Instruction/Frequently-asked-questions.md
    • Updated Q56 to reflect check_dataset_strategy parameter changes in Swift 3.0+.
    • Updated Q72 to clarify get_default_template_type support in Swift 3.0+.
    • Updated Q78 with a link to an example for fine-tuning deepseek R1 671B.
    • Removed Q83 regarding LoRA-trained reward models.
    • Updated Q161 to reference save_strategy for saving checkpoints per epoch in Megatron-Swift.
    • Updated Q12 to specify how to set request timeouts for Swift 3.0+ deployment inference.
  • docs/source_en/Instruction/Frequently-asked-questions.md
    • Updated Q56 to reflect check_dataset_strategy parameter changes in Swift 3.0+.
    • Updated Q72 to clarify get_default_template_type support in Swift 3.0+.
    • Updated Q78 with a link to an example for fine-tuning deepseek R1 671B.
    • Removed Q83 regarding LoRA-trained reward models.
    • Updated Q161 to reference save_strategy for saving checkpoints per epoch in Megatron-Swift.
    • Updated Q12 to specify how to set request timeouts for Swift 3.0+ deployment inference.
Activity
  • No specific activity (comments, reviews, or progress updates) has been recorded for this pull request yet.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates the FAQ documents in both Chinese and English. The changes include clarifying version applicability, updating answers for newly supported features, removing an outdated question, and improving the phrasing of questions and answers in the English version. I've found a couple of minor issues in the English FAQ file: a typo in a code snippet and a link pointing to a less specific documentation page. I've provided suggestions to fix them. Overall, these are good improvements to the documentation.

### Q72: Does swift3.0 not support get_default_template_type?
Please check `model.model_meta.template`, the information is available in `model.model_meta` and `model.model_info`.
### Q72: Is get_default_template_type no longer supported in SWIFT versions 3.0 and later?
Please check `model.model_meta.templat`e. The information is stored in `model.model_meta` and `model.model_info`.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

There's a typo in the code snippet. model.model_meta.template should be model.model_meta.template.

Suggested change
Please check `model.model_meta.templat`e. The information is stored in `model.model_meta` and `model.model_info`.
Please check `model.model_meta.template`. The information is stored in `model.model_meta` and `model.model_info`.

```
Saving checkpoints per epoch is not yet supported.
### Q161: With the script below, can megatron-swift save checkpoints per epoch?
Yes, please refer to the command-line parameter [save_strategy](https://swift.readthedocs.io/en/latest/Instruction/Command-line-parameters.html).
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The link for save_strategy points to the general command-line parameters documentation. Since the question is about megatron-swift, it would be more helpful to link directly to the Megatron-SWIFT command-line parameters documentation where save_strategy is described.

Suggested change
Yes, please refer to the command-line parameter [save_strategy](https://swift.readthedocs.io/en/latest/Instruction/Command-line-parameters.html).
Yes, please refer to the command-line parameter [save_strategy](https://swift.readthedocs.io/en/latest/Megatron-SWIFT/Command-line-parameters.html).

@slin000111
Copy link
Collaborator Author

/gemini review

@gemini-code-assist
Copy link
Contributor

Note

Gemini is unable to generate a review for this pull request due to the file types involved not being currently supported.

@Jintao-Huang
Copy link
Collaborator

/gemini review

@gemini-code-assist
Copy link
Contributor

Note

Gemini is unable to generate a review for this pull request due to the file types involved not being currently supported.

@slin000111 slin000111 merged commit 85383c4 into modelscope:main Mar 1, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants